Method and device for determining a list of items to be explained, computer device and storage medium

Abstract

This disclosure provides a method, apparatus, computer device, and storage medium for determining a list of items to be explained, belonging to the field of network technology. The technical solution provided by the embodiments of this disclosure, when a first object adds a first item to the list of items to be explained, displays an item combination consisting of the first item and at least one second item, allowing the first object to view the items included in the combination. Since the items in the combination conform to a common selling logic, it encourages the first object to add all items involved in the combination to the list of items to be explained. This facilitates the first object's subsequent explanation of the item combination in the target live stream room based on the list of items to be explained, improving the efficiency of the first object's item selection. It eliminates the need for manual selection of items from numerous items to add to the list of items to be explained, avoiding the difficulty in determining the items in the list of items to be explained, reducing a large number of interactive operations, and improving interactive efficiency.

Description

Technical Field

[0001] This disclosure relates to the field of network technology, and in particular to a method, apparatus, computer equipment, and storage medium for determining an explanatory list of items. Background Technology

[0002] With the development of live streaming platforms, streamers can explain products through live broadcasts, encouraging viewers to place orders and achieving product conversion. Streamers can explain not only single items but also combinations of multiple items, allowing viewers to place orders for those combinations. Live streaming platforms offer item selection functions, allowing streamers to choose which items to explain. However, if a streamer wants to explain a specific item combination, they need to manually compare and add each item to the list, which is time-consuming and leads to delays in finalizing the list. This method involves a large amount of interaction, resulting in low human-computer interaction efficiency. Summary of the Invention

[0003] This disclosure provides a method, apparatus, computer device, and storage medium for determining an explanatory item list, which can improve the efficiency of human-computer interaction. The technical solution of this disclosure is as follows: According to one aspect of the embodiments of this disclosure, a method for determining an explanatory item list is provided, comprising: The first item is displayed on the item page, which is used to provide multiple items for the target live stream; In response to the first object's list addition operation for the first item, the first item is added to the list of explanatory items in the target live stream room; Based on the item page, the agent displays an item combination provided by the first item, the item combination including the first item and at least one second item, the at least one second item conforming to a co-selling logic with the first item, and the agent is used to provide the item combination through a large model; In response to the operation of adding items to the list of the item combination, the at least one second item is added to the list of explanatory items.

[0004] According to one aspect of the embodiments of this disclosure, an apparatus for determining an explanatory list of items is provided, comprising: The page display module is configured to display a first item on an item page, which is used to provide multiple items for the target live stream room; The item addition module is configured to add the first item to the list of explanatory items in the target live broadcast room in response to a list addition operation of the first object for the first item. The combined display module is configured to display an item combination provided by an agent based on the first item, on the item page. The item combination includes the first item and at least one second item, and the at least one second item conforms to a co-sale logic with the first item. The agent is used to provide the item combination through a large model. The first combination addition module is configured to add the at least one second item to the explanatory item list in response to a list addition operation of the item combination.

[0005] In some embodiments, the combined display module is configured to perform at least one of the following: Based on the item page, the agent displays a first item combination provided by the first item, where the items in the first item combination have complementary functions. Based on the item page, the agent displays a second item combination provided by the first item, wherein the items in the second item combination belong to the same usage scenario and have a combination relationship in the usage scenario; Based on the item page, the agent displays a third item combination provided by the first item, where the items in the third item combination have a linked purchase relationship. Based on the item page, the agent displays a fourth item combination provided by the agent based on the first item, wherein there is a price gradient among the items in the fourth item combination.

[0006] In some embodiments, the combined display module is configured to perform any of the following: Based on the item page, the system displays the item combination obtained by the agent through a large model, which calculates feature similarity based on the item features of the first item and multiple candidate items. Based on the item page, the combination of items is displayed, which is identified by the agent through the large model based on the historical orders related to the first item. Based on the item page, the system displays the item combination obtained by the agent through the large model based on the item features of the first item and multiple candidate items, using a joint sales logic analysis.

[0007] In some embodiments, the apparatus further includes: The explanation display module is configured to display explanation information for the item combination generated by the intelligent agent through a large model based on the item page. The explanation information includes a summary of the item functions of the item combination and the reasons for selling them together.

[0008] In some embodiments, the item combination includes a combined image, which is generated by the agent based on the item images corresponding to the first item and the at least one second item, respectively.

[0009] In some embodiments, the combined display module is configured to display viewing prompt controls corresponding to at least one second item in the item combination in a preset adjacent area; and to display the item details page of the second item in response to a triggering operation of the viewing prompt control for any second item.

[0010] In some embodiments, the explanatory information is obtained through the following steps: The intelligent agent calls the large model to analyze the preset generation rules, the joint sales logic information of the item combination, and the item characteristics corresponding to the first item and the at least one second item, respectively, to obtain the explanation information. The preset generation rules are used to instruct the large model to gradually generate the opening remarks, item function summary, joint sales reasons, and order generation prompts that constitute the explanation information.

[0011] In some embodiments, the explanatory information is obtained through the following steps: The intelligent agent calls the large model to analyze the preset generation rules, the joint sales logic information of the item combination, the item characteristics corresponding to the first item and the at least one second item, and the live broadcast scene information to obtain the explanation information. The preset generation rules are used to instruct the large model to gradually generate the opening remarks, item function summary, joint sales reasons and order generation prompts to constitute the explanation information. The live broadcast scene information is used to instruct the large model to generate explanation information that conforms to the current live broadcast scene.

[0012] According to one aspect of the embodiments of this disclosure, an apparatus for determining an explanatory list of items is provided, comprising: The combination determination module is configured to respond to the first object's list addition operation for the first item, add the first item to the list of explanatory items in the target live broadcast room, and call the intelligent agent to determine at least one second item that conforms to the co-sale logic with the first item through the large model. A combination providing module is configured to provide the first object with a combination of items consisting of the first item and the at least one second item; The second combination addition module is configured to add the at least one second item to the explanatory item list in response to a list addition operation of the item combination.

[0013] In some embodiments, the combination determination module is configured to perform any of the following: The intelligent agent is invoked to calculate the feature similarity between the first item and multiple candidate items based on the item features of the first item and multiple candidate items through the large model, and to determine at least one second item whose feature similarity reaches a preset threshold from the multiple candidate items. The intelligent agent is invoked to identify, based on the historical orders related to the first item, at least one second item that has a purchase relationship with the first item through the large model; The intelligent agent is invoked to perform a co-sale logic analysis based on the characteristics of the first item and multiple candidate items through the large model, and to determine at least one second item from the multiple candidate items that conforms to the co-sale logic with the first item.

[0014] In some embodiments, the item features corresponding to the first item and the plurality of candidate items respectively include basic attribute features, functional features, applicable population features, and scenario features extracted by the intelligent agent from the item details information corresponding to the first item and the plurality of candidate items respectively.

[0015] According to another aspect of the embodiments of the present disclosure, a computer device is provided, the computer device comprising: One or more processors; Memory used to store the executable program code of the processor; The processor is configured to execute the program code to implement the method for determining the item list as explained above.

[0016] According to another aspect of the present disclosure, a computer-readable storage medium is provided, which, when the program code in the computer-readable storage medium is executed by a processor of a computer device, enables the computer device to perform the above-described method for determining the list of explanatory items.

[0017] According to another aspect of the present disclosure, a computer program product is provided, including a computer program / instructions that, when executed by a processor, implement the method for determining the list of explanatory items described above.

[0018] The technical solution provided in this disclosure, when a first object adds a first item to the item list for explanation, displays an item combination consisting of the first item and at least one second item, allowing the first object to view the items included in the item combination. Since the items in the item combination conform to the common selling logic, it can encourage the first object to add all items involved in the item combination to the item list for explanation. This facilitates the first object to explain the item combination in the target live broadcast room based on the item list for explanation, improving the efficiency of the first object's product selection. It eliminates the need for manual selection of items from a large number of items to add to the item list, avoids the difficulty in determining the items in the item list for explanation, avoids a large number of interactive operations, and improves the efficiency of human-computer interaction.

[0019] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0020] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0021] Figure 1 This is a schematic diagram illustrating an implementation environment for a method for determining an item list, according to an exemplary embodiment.

[0022] Figure 2 This is a flowchart illustrating a method for determining an item list according to an exemplary embodiment.

[0023] Figure 3 This is an illustration of an item details page provided in this public disclosure.

[0024] Figure 4 This is an illustration of an item details page provided in this public disclosure.

[0025] Figure 5 This is a flowchart illustrating yet another method for determining a list of items, according to an exemplary embodiment.

[0026] Figure 6 This is a block diagram illustrating an apparatus for determining an explanatory list of items according to an exemplary embodiment.

[0027] Figure 7 This is a block diagram illustrating yet another apparatus for determining an explanatory list of items, according to an exemplary embodiment.

[0028] Figure 8 This is a block diagram illustrating a terminal according to an exemplary embodiment.

[0029] Figure 9This is a block diagram illustrating a server according to an exemplary embodiment. Detailed Implementation

[0030] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0031] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0032] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, data stored, data displayed, etc.) and signals involved in this disclosure are all authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0033] Figure 1 This is a schematic diagram illustrating an implementation environment for a method for determining an item list, according to an exemplary embodiment. See also: Figure 1 The implementation environment specifically includes: terminal 101 and server 102. Terminal 101 and server 102 can be connected directly or indirectly through wired or wireless communication, which is not limited herein.

[0034] Terminal 101 is one implementation of a computer device, and can be at least one of the following: a smartphone, smartwatch, desktop computer, laptop, MP3 player, MP4 player, and laptop computer. Terminal 101 runs a specific application that supports the narration of a list of items. Users can log in to this application through Terminal 101 to access the services provided by the application. For example, users can add items to the narration list through the application on Terminal 101; of course, this application could be a live streaming application, etc.

[0035] Terminal 101 generally refers to one of a plurality of terminals; this embodiment uses terminal 101 as an example. Those skilled in the art will understand that the number of terminals can be more or less. For example, there may be several terminals, or dozens or hundreds of terminals, or even more. This disclosure does not limit the number of terminals or the type of device.

[0036] Server 102 is at least one of a single server, multiple servers, a cloud computing platform, and a virtualization center. Server 102 provides backend services for an application that supports adding items to the item list. Server 102 can connect to terminal 101 via a wireless or wired network, and server 102 can provide the terminal with item combinations, etc. In some embodiments, the number of servers may be more or less, and this disclosure does not limit this. Of course, server 102 may also include other functional servers to provide more comprehensive and diverse services.

[0037] Figure 2 This is a flowchart illustrating a method for determining an item list according to an exemplary embodiment. See also: Figure 2 Taking a computer device as an example, the method includes the following steps: In step 201, the terminal displays the first item on the item page, which is used to provide items for the target live streaming room.

[0038] The target live stream room can refer to the live stream room of the first target, who can be a streamer or host on a live streaming platform who explains an item. The item page can be an item list page provided by the live streaming platform or the item details page of the first item. For example, if the item page is an item list page, it can display multiple items, allowing the first target to select the item to be explained in the target live stream room. Alternatively, if the item page is the item details page of the first item, it can display detailed information about the first item, allowing the first target to select that item as the item to be explained in the target live stream room.

[0039] In step 202, the terminal responds to the first object's list addition operation for the first item by adding the first item to the list of explanatory items in the target live broadcast room.

[0040] The item page can display an item addition control for the first item. The item addition operation for the first object for the first item can be: the triggering operation of the item addition control for the first object for the first item.

[0041] The item list can include items selected by the first target to be explained. The first target can also select items to be explained in the target live stream.

[0042] In step 203, the terminal displays an item combination provided by the agent based on the first item on the item page. The item combination includes the first item and at least one second item. The at least one second item conforms to the co-selling logic with the first item. The agent is used to provide the item combination through a large model.

[0043] In this combination, each second item in the item combination must conform to the co-sale logic with the first item. For example, the large model can determine whether the two items conform to the co-sale logic based on the item characteristics of the first item and the candidate items, such as whether they have complementary functions, have a related purchase relationship, belong to the same use scenario and have a matching relationship in the use scenario, have a price gradient, or belong to the same style. If they do, the candidate item can be used as the second item in the item combination with the first item. For a detailed explanation, please refer to the following description.

[0044] This large model is an artificial intelligence model. In some embodiments, it can be a multimodal large model, which refers to a large model capable of simultaneously processing and understanding multiple different modalities. It can be pre-trained on a large amount of multimodal data. In an optional implementation, the large model may include an encoder, a decoder, a self-attention layer, and a feed-forward neural network. The encoder is mainly used to convert input data (usually in sequence form) into vector representations. This process can capture the semantic features of the input data. The decoder is responsible for converting the intermediate representations generated by the encoder into output data (usually in sequence form). The self-attention layer is a mechanism that allows the model to pay attention to other positions in the sequence to better encode the information of the current position. The feed-forward neural network can perform nonlinear transformations on the output of the self-attention layer to enhance the model's expressive power. The various parts work together, enabling the model built on them to perform well in various complex processing tasks, such as natural language processing, computer vision, speech recognition, machine translation, text summarization, and intelligent question answering.

[0045] In step 204, in response to the operation of adding items to the list, the terminal adds at least one second item to the list of explanatory items.

[0046] The item page can display a control for adding items to a combination. The operation of adding items to the list can refer to the triggering operation of the control for adding items to a combination. Thus, the terminal can respond to the triggering operation of the control for adding items to a combination by the first object and add at least one second item to the list of items.

[0047] In this embodiment of the disclosure, when the first object adds the first item to the item list for explanation, an item combination consisting of the first item and at least one second item is displayed for the first object to view the items included in the item combination. Since the items in the item combination conform to the common selling logic, it can encourage the first object to add all items involved in the item combination to the item list for explanation. This makes it easier for the first object to explain the item combination in the target live broadcast room based on the item list for explanation, thereby realizing the sale of the item combination. This improves the efficiency of the first object's product selection, eliminating the need for manual selection of items from a large number of items to add to the item list for explanation. It avoids the difficulty in determining the items in the item list for explanation, avoids a large number of interactive operations, improves the efficiency of human-computer interaction, and enables the first object to sell the item combination by explaining it in the target live broadcast room. Compared with selling a single item, this can increase the average order value and item conversion rate.

[0048] Items typically have different types of relationships, and based on these different types of relationships, there can be different ways to combine them, thus forming different types of combinations. In some embodiments, the step 203 above, displaying the item combination provided by the agent based on the first item on the item page, may include at least one of the following: displaying the first item combination provided by the agent based on the first item on the item page, where the items in the first item combination have complementary functions; displaying the second item combination provided by the agent based on the first item on the item page, where the items in the second item combination belong to the same usage scenario and have a pairing relationship in the usage scenario; displaying the third item combination provided by the agent based on the first item on the item page, where the items in the third item combination have a linked purchase relationship; displaying the fourth item combination provided by the agent based on the first item on the item page, where there is a price gradient among the items in the fourth item combination; and displaying the fifth item combination provided by the agent based on the first item on the item page, where the items in the fifth item combination belong to the same style. Among these, complementary product functions refer to items that, while each serving a different purpose, work together to fulfill a specific need. For example, a product set might include calcium tablets, vitamin D tablets, and magnesium tablets. Calcium tablets function as XXX, vitamin D tablets as XXX, and magnesium tablets as XXX. Together, they fulfill the need for XXX. Items belonging to the same usage scenario and having a complementary relationship within that scenario, such as home, commuting, or outdoor use, can be combined. In a camping scenario, a camping lamp and a folding chair can be used together. Item sets based on shared usage scenarios can inspire viewers' interest in those scenarios, increasing their willingness to purchase the set. Items with a cross-purchase relationship, such as consumers often buying a phone case along with their phone, can also be combined. Item sets based on this cross-purchase relationship can encourage viewers to purchase the core item along with the complementary item, thereby increasing average order value and conversion rate. The existence of price gradients among items in the fourth item combination refers to items with different price tiers within the combination. For example, a fourth item combination might contain low-priced and high-priced items. The low-priced items can be low-profit items, lowering the purchase threshold and attracting viewers to the live stream, thereby boosting sales. The high-priced items can be high-profit items, increasing profitability. Combining items with different price tiers in the combination can maximize overall profit. Item combinations built around items of the same style help strengthen visual and aesthetic consistency, stimulating viewers' desire for a specific aesthetic style and increasing their willingness to purchase the item combination.The aforementioned item combinations based on the first item may include at least one of the following: a first item combination, a second item combination, a third item combination, a fourth item combination, and a fifth item combination. The different types of relationships between the items in the first item combination, the second item combination, the third item combination, the fourth item combination, and the fifth item combination correspond to different combination methods. Therefore, the item combinations based on the first item may involve one or more combination methods, namely, combination based on the item's function, combination based on the item's usage scenario, combination based on the item's price, combination based on whether the item is purchased as part of a bundled purchase, and combination based on the item's style. When the item combinations based on the first item involve multiple combination methods, it helps to cover the various purchasing motivations and decision-making paths of the audience in the live broadcast room, thereby increasing the average order value and conversion rate.

[0049] In some embodiments, there can be multiple different ways to filter second items from multiple candidate items, thereby constructing an item combination based on the first item and at least one second item. Step 203 above, based on the item page, displays the item combination provided by the agent based on the first item, which may include any of the following: (1) Based on the item page, the display agent calculates the feature similarity of the first item and multiple candidate items using a large model. The item features corresponding to the first item and multiple candidate items can be: basic attribute features, functional features, applicable user features, and scene features extracted by the agent from the item details information corresponding to the first item and multiple candidate items. The large model can calculate the feature similarity between the first item and multiple candidate items based on at least one of the functional features, scene features, and style features of the first item and multiple candidate items. For example, based on the functional features corresponding to the first item and multiple candidate items, the feature similarity between the first item and multiple candidate items is calculated, and the candidate items whose feature similarity reaches a preset threshold are used as the second item, that is, the candidate items with similar functions to the first item are used as the second item. This method can discover the implicit association of items from the features of the items, and form item combinations based on items with complementary functions, belonging to the same scene, or belonging to the same style, so that the items in the item combination conform to the common purchase logic, which can achieve accurate construction of item combinations, and ultimately improve the conversion rate of item combinations. Moreover, this method has a strong generalization ability and can also make reasonable inferences based on features for new products.

[0050] (2) Based on the item page, the intelligent agent identifies the item combination obtained by the big model based on the historical orders related to the first item. The historical orders related to the first item can include orders directly and indirectly related to the first item. The historical orders directly related to the first item are those containing the first item. The orders indirectly related to the first item can refer to historical orders that are consecutive to the historical orders containing the first item. For example, if the time interval between the generation time of a certain historical order and the generation time of the historical order containing the first item is less than a preset time interval, then the historical order and the historical order containing the first item are consecutive. The big model can arrange the set of items in the historical orders related to the first item into a sequence. Through the autoregressive generation mechanism, it learns the conditional co-occurrence probability between items, so that at least one second item that co-occurs with the first item multiple times with a high conditional probability can be determined from these item sets. That is, at least one second item that is purchased in conjunction with the first item multiple times can be determined from these item sets. In this approach, the large model constructs item combinations by mining the co-occurrence relationships of items in historical orders. It can directly learn associated purchase patterns from real transaction behavior, capture user preferences and related needs, and generate item combinations that better match user purchasing habits, thereby effectively improving the conversion rate and average order value. It should be noted that the aforementioned historical orders are obtained with the user's full authorization. The terminal can provide authorization to the user through pop-up windows or other means; this embodiment does not limit this approach.

[0051] (3) Based on the item page, the display agent obtains the item combination by performing a joint selling logic analysis based on the item characteristics of the first item and multiple candidate items through a large model. The large model can directly perform joint selling logic analysis based on the item characteristics of the first item and multiple candidate items. For example, if the first item and candidate items meet at least one of the following criteria: complementary usage function, belonging to the same usage scenario and having a paired usage relationship within the usage scenario, having a price gradient, or belonging to the same style, then the candidate item is designated as the second item. Then, it is determined whether any candidate item not yet designated as the second item conforms to the joint selling logic with either the first item or any of the already designated second items. That is, it is determined whether they meet at least one of the following criteria: complementary usage function, belonging to the same usage scenario and having a paired usage relationship within the usage scenario, having a price gradient, or belonging to the same style. If they do, the candidate item is designated as the second item. Thus, the large model can gradually determine multiple second items that conform to the joint selling logic with the first item. In this method, the large model, through a deep understanding of the multi-dimensional characteristics of items, can deeply explore the logical relationships between items, forming combinations that conform to the joint selling logic, thereby improving the logical rationality of the item combinations.

[0052] To facilitate the first-user's understanding of the reasons for selling the item combination together and to help them decide whether to select the items included in the combination, in some embodiments, the method may further include: displaying explanatory information about the item combination generated by the agent through a large model on the item page. This explanatory information may include a summary of the functions of the items in the combination and the reasons for selling them together. The summary of the functions of all the items included in the combination is a summary of their functions, such as "Calcium tablets function as XXX, Vitamin D function as XXX, and Magnesium function as XXX." The reasons for selling them together are the reasons for combining the items in the combination, such as "Eating these three together achieves XXX effect." This explanatory information allows the first-user to understand the functions of the items in the combination and the reasons for selling them together, encouraging them to add the items in the combination to their list of explained items, improving their decision-making efficiency. Furthermore, this explanatory information can be used as a reference for the first-user, saving them significant time in organizing their own explanations and increasing the conversion rate of the target live stream.

[0053] The explanation information can be obtained by following these steps: The agent calls the large model to analyze the preset generation rules, the co-sale logic information of the item combination, and the item characteristics corresponding to the first item and at least one second item, and obtains the explanation information. The preset generation rules are used to instruct the large model to gradually generate the opening remarks, item function summary, co-sale reasons, and order generation prompts that constitute the explanation information.

[0054] The co-sale logic information for the item combination can be generated through the following steps: The agent analyzes the co-sale logic based on the characteristics of the first item and multiple candidate items using a large model. Simultaneously, it identifies at least one second item from the candidate items that conforms to the co-sale logic of the first item, generating co-sale logic information. This co-sale logic information describes the reasons for the co-sale of the first item and at least one second item, that is, it describes the shared relationships among the items in the item combination. These relationships can include at least one of the following: complementary functions, belonging to the same usage scenario and having a paired usage relationship within that scenario, the existence of a price gradient, or belonging to the same style. Of course, if the item combination includes at least three items, the co-sale logic information can also describe the relationships among the items in the sub-item combinations within the item combination. For example, if the item combination includes four items, the co-sale logic information can also describe the relationship between any two items and the shared relationship between any three items. Thus, the large model can generate the co-sale reasons in the explanatory information based on this co-sale logic information.

[0055] To ensure the generated explanation information aligns with the current livestream scenario, in some embodiments, the explanation information can be obtained through the following steps: An intelligent agent invokes a large model to analyze preset generation rules, the co-sale logic information of item combinations, the item characteristics corresponding to the first item and at least one second item, and the livestream scenario information to obtain the explanation information. The preset generation rules instruct the large model to progressively generate an opening statement, a summary of item functions, reasons for co-sale, and order generation prompts to constitute the explanation information. The livestream scenario information instructs the large model to generate explanation information that conforms to the current livestream scenario. For example, the livestream scenario information could be a new product launch, a holiday promotion, or daily sales. This livestream scenario information can be extracted by the intelligent agent from the information of a pre-set livestream plan by the first object, such as from the title of the livestream plan. Alternatively, the livestream scenario can be determined based on the current time; for example, if the current time point is during a holiday promotion, the livestream scenario information would be "Holiday Promotion." When neither of these methods can obtain the livestream scenario information, preset livestream scenario information such as "Daily Sales" can be used as the current livestream scenario information. In this embodiment of the disclosure, by inputting the live streaming scene information into a large model, the generated explanation information can be adapted to the current live streaming scene, thus making the explanation information real-time.

[0056] To enable viewers to intuitively perceive the discounts offered by item bundles, in some embodiments, preset generation rules can be used to instruct the large model to progressively generate introductory information, a summary of item functions, reasons for joint sales, price comparisons, and order generation prompts. This price comparison involves comparing the bundled price with the total price obtained by combining the individual prices of the items in the bundle. Through this price comparison, viewers can intuitively perceive the discounts offered by purchasing the bundle compared to purchasing individual items, encouraging them to make the purchase decision and thereby increasing conversion rates and average order value.

[0057] Specifically, prompts can be generated based on a preset prompt template, the common sales logic of item combinations, and the item characteristics corresponding to the first item and at least one second item. The preset prompt template includes preset generation rules. The prompts are input into a large model, which then generates explanatory information. For example, the item characteristics corresponding to the first item and at least one second item may include basic attribute characteristics such as name and price, functional characteristics, and target audience characteristics.

[0058] For example, the preset prompt word template is: You are a professional live-streaming sales script writing tool. Please generate a suitable script for explaining product combinations during a live stream based on the following information.

[0059] Current product: {AAA}, Key selling points: {BBB}, Price: {CCC} Packaged items: {DDD}, Key selling point: {EEE}, Price: {FFF} Collocation logic: {GGG} Live streaming scenario: {HHH} The script structure must include the following content, and the order cannot be changed: Opening remarks (to attract the audience's attention and introduce the theme of the group) Product Features Summary (Summarize the product's selling points) Combinatorial logic explanation (explaining why these items are suitable to be purchased / used together) Price / Discount Comparison (Compare bundled prices with individual item prices to highlight the discount). Order placement instructions (guiding viewers on how to place an order for a combination). Specifically, the name of the first item can be filled in {AAA}, the functional characteristics and applicable audience characteristics of the first item can be filled in {BBB}, the price of the first item can be filled in {CCC}, the name of the second item can be filled in {DDD}, the functional characteristics and applicable audience characteristics of the second item can be filled in {EEE}, the price of the second item can be filled in {FFF}, the co-sale logic information can be filled in {GGG}, and the live broadcast scene information can be filled in {HHH}, which together form the prompt words.

[0060] To facilitate the first object's intuitive understanding of the items included in the item combination, in some embodiments, the item combination may include a combination image. The combination image is generated by an agent based on the item images corresponding to the first item and at least one second item, respectively. The combination image may contain images corresponding to the first item and at least one second item, respectively. The combination image may be generated by the agent calling a large model based on the item images corresponding to the first item and at least one second item, respectively.

[0061] To facilitate a first object's detailed understanding of the second item in the item set, the method may further include: displaying at least one viewing prompt control corresponding to each of the at least one second item in a preset adjacent area; and displaying the item details page of the second item in response to a triggering operation of the viewing prompt control for any second item. In this embodiment, displaying viewing prompt controls near the second item facilitates the first object in establishing an intuitive spatial mapping relationship, shortens the path from noticing the second item to obtaining its detailed information, reduces the cognitive burden on the first object, and helps improve decision-making efficiency.

[0062] To facilitate the first user's understanding of item combinations by combining multi-dimensional information, in some embodiments, displaying the item combinations provided by the agent based on the first item on the item page may include: displaying an item combination page on the item page, and displaying the item combinations provided by the agent based on the first item in a first display area of ​​the item combination page. The method may also include: displaying explanatory information about the item combinations generated by the agent through a large model in a second display area of ​​the item combination page. The item combination page may be displayed in the form of a pop-up window, etc. In this embodiment of the disclosure, by displaying combination images and explanatory information on the item combination page, the efficiency of information transmission for item combinations can be improved, making it easier for the first user to understand what the item combination is and the reasons for its inclusion, thereby encouraging the first user to make the decision to add the item combination to the list of explanatory items.

[0063] The following example, using the item details page with the item page as the first item, illustrates the specific implementation of the method for determining the item list.

[0064] Figure 3 This is a schematic diagram of the item details page of the first item provided in this disclosure. On this item details page 300, an item-adding control 301 for the first item, such as Vitamin D tablets, can be displayed. The terminal can respond to a trigger operation by the first object on the item-adding control 301, such as... Figure 4 As shown, the item combination page 401 is displayed on the item details page 300. The first display area 402 of the item combination page 401 displays a combination image of the item combination, which consists of a first item, such as vitamin D tablets, and two second items, such as calcium tablets and magnesium tablets. A viewing prompt control 4031 is displayed in a preset adjacent area of ​​the calcium tablets in the combination image. The terminal can respond to a trigger operation on the viewing prompt control 4031 to display the calcium tablets' item details page. The terminal can also display a viewing prompt control 4032 in a preset adjacent area of ​​the magnesium tablets in the combination image. Responding to a trigger operation on the viewing prompt control 4032 by a first object, the magnesium tablets' item details page is displayed. The terminal can also display explanatory information about the item combination in the second display area 404 of the item combination page 401. The terminal can also display a combination addition control 405 in the second display area 404. The terminal can respond to a trigger operation on the combination addition control 405 to add the calcium and magnesium tablets to the explanatory item list.

[0065] Figure 5 This is a flowchart illustrating another method for determining an item list according to an exemplary embodiment. The technical solution of this embodiment can be executed by a server, and the method may include the following steps: In step 501, in response to the first object's list addition operation for the first item, the first item is added to the list of explanatory items in the target live broadcast room, and the agent is invoked to determine at least one second item that conforms to the co-sale logic with the first item through the large model.

[0066] For a detailed explanation of this step, please refer to steps 201, 202, and 203 above. They will not be repeated here.

[0067] In step 502, a combination of items consisting of a first item and at least one second item is provided to the first object.

[0068] In step 503, in response to the list addition operation for the item combination, at least one second item is added to the explanatory item list.

[0069] For a detailed explanation of this step, please refer to step 204 above, which will not be repeated here.

[0070] In this embodiment of the disclosure, when the first object adds the first item to the explanation item list, an item combination consisting of the first item and at least one second item is provided. Since the items in the item combination conform to the common selling logic, it can encourage the first object to add all items involved in the item combination to the explanation item list. This facilitates the first object to explain the item combination in the target live broadcast room based on the explanation item list, thereby realizing the sale of the item combination. This improves the efficiency of the first object's product selection, eliminating the need for manual selection of items from a large number of items to add to the explanation item list. It also avoids the difficulty in determining the items in the explanation item list, avoids a large number of interactive operations, and improves the efficiency of human-computer interaction. Furthermore, the first object can realize the sale of the item combination by explaining it in the target live broadcast room, which can increase the average order value and item conversion rate compared to selling a single item.

[0071] In some embodiments, a variety of different methods can be used to filter second items from multiple candidate items to construct an item combination based on the first item and at least one second item. The calling agent determines, through a large model, at least one second item that conforms to the co-selling logic with the first item, including any of the following: (1) Call the agent to calculate the feature similarity between the first item and multiple candidate items based on the item features of the first item and multiple candidate items through the large model, and determine at least one second item whose feature similarity reaches a preset threshold from multiple candidate items.

[0072] (2) Call the intelligent agent to identify at least one second item that has a related purchase relationship with the first item by using the large model based on the historical orders related to the first item.

[0073] (3) Call the agent to perform a joint sale logic analysis based on the characteristics of the first item and multiple candidate items through the large model, and determine at least one second item from the multiple candidate items that conforms to the joint sale logic with the first item.

[0074] The item features corresponding to the first item and multiple candidate items can be: basic attribute features, functional features, applicable audience features, and scenario features extracted by the agent from the item details information corresponding to the first item and multiple candidate items. Item features can be in the form of structured tags or semantic representations, etc. Item details information can include the item's title, category, price, specifications, core function description, and item image, etc. The basic attribute features extracted by the agent from the item details information can include one or more features such as category, price, and brand. The agent can call a natural language processing model or the aforementioned large model to extract basic attribute features, functional features, and applicable audience features based on the text information such as the item's title, price, specifications, and core function description. For example, basic attribute features may include one or more features such as category, price, or brand; functional features describe the item's function, such as the function of sunscreen being chemical sunscreen; and applicable audience features describe the characteristics of the people to whom the item is applicable, such as the age, gender, and region of the applicable audience. The agent can invoke a multimodal model to extract scene features from item images. Scene features can be such as home, commuting, or outdoor conditions. Alternatively, these scene features can be extracted from textual information such as titles in item details by the agent using a larger model; this disclosure does not impose any limitations on this. Furthermore, the agent can also invoke a multimodal model to extract style features from item images. This multimodal model can be the same as or a different model from the aforementioned larger model.

[0075] The aforementioned calculation of feature similarity between a first item and multiple candidate items using a large model based on their item features can be interpreted as follows: The large model calculates feature similarity between the first item and multiple candidate items based on at least one of their functional features, scene features, and style features. For example, based on the functional features corresponding to the first item and multiple candidate items respectively, the feature similarity between the first item and each candidate item is calculated. Candidate items whose feature similarity reaches a preset threshold are then designated as second items; that is, candidate items with similar functions to the first item are designated as second items. For instance, if the first item is calcium tablets and the candidate items are vitamin D tablets, since the functions of calcium tablets and vitamin D tablets are similar, vitamin D tablets can be combined with the first item as a second item. Similarly, the large model can calculate feature similarity between the first item and multiple candidate items based on their scene and style features. Candidate items whose feature similarity reaches a preset threshold are then designated as second items, allowing candidate items with similar scenes and styles to the first item to be designated as second items. This approach allows us to discover implicit connections between items based on their characteristics. Items can be grouped together based on complementary functions, belonging to the same scenario, or sharing the same style. This ensures that the items in the group conform to a shared purchasing logic, enabling precise construction of item groups and ultimately improving their conversion rate. Furthermore, this method has strong generalization capabilities and can make reasonable inferences based on characteristics even for new products.

[0076] Of course, the agent can also call the semantic matching model to calculate the feature similarity between the first item and multiple candidate items based on the item features of the first item and multiple candidate items, and determine at least one second item from the multiple candidate items whose feature similarity reaches a preset threshold.

[0077] The historical orders related to the first item mentioned above can include orders directly and indirectly related to the first item. Historical orders directly related to the first item are those containing the first item. Orders indirectly related to the first item can refer to historical orders that are consecutive to those containing the first item. For example, if the time interval between the generation time of a certain historical order and the generation time of a historical order containing the first item is less than a preset time interval, then the historical order and the historical order containing the first item are consecutive. The large model can arrange the set of items in the historical orders related to the first item into a sequence. Through an autoregressive generation mechanism, it learns the conditional co-occurrence probability between items, thereby identifying at least one second item that has multiple high conditional co-occurrences with the first item from these item sets. In other words, it identifies at least one second item that has been purchased in conjunction with the first item multiple times from these item sets.

[0078] The aforementioned method of invoking an intelligent agent to perform joint sales logic analysis based on the characteristics of a first item and multiple candidate items using a large model can be described as follows: The intelligent agent uses the large model to perform joint sales logic analysis based on the basic attribute characteristics, functional characteristics, applicable user characteristics, and scenario characteristics of the first item and multiple candidate items. For example, if the first item and candidate items meet at least one of the following criteria: complementary usage functions, belonging to the same usage scenario and having a paired usage relationship within that scenario, having a price gradient, or belonging to the same style, then that candidate item is designated as the second item. Then, it is determined whether any candidate item not yet designated as the second item conforms to the joint sales logic with the first item or any of the already designated second items. That is, it is determined whether they meet at least one of the following criteria: complementary usage functions, belonging to the same usage scenario and having a paired usage relationship within that scenario, having a price gradient, or belonging to the same style. If they do, then that candidate item is designated as the second item. Thus, the large model can gradually determine multiple second items that conform to the joint sales logic with the first item. In this approach, the large model, through a deep understanding of the multi-dimensional characteristics of items, can deeply explore the logical relationships between items, forming combinations that conform to the joint sales logic, thereby improving the logical rationality of the item combinations.

[0079] In addition, the large model performs co-sale logic analysis based on the item characteristics of the first item and multiple candidate items. While determining at least one second item from the multiple candidate items that conforms to the co-sale logic with the first item, it can also generate co-sale logic information. The information contained in this co-sale logic information can be seen in the previous description and will not be repeated here.

[0080] To facilitate the first target audience's understanding of the reasons for selling the item combination together and to help them decide whether to select items from the combination, in some embodiments, the method may further include: invoking an intelligent agent to generate explanatory information about the item combination through a large model, and providing this information to the first target audience. This explanatory information may include a summary of the item functions in the combination and the reasons for joint sale. Specifically, the intelligent agent can invoke the large model to analyze preset generation rules, the joint sale logic of the item combination, and the item characteristics corresponding to the first item and at least one second item to obtain the explanatory information. The preset generation rules instruct the large model to progressively generate an opening statement, a summary of item functions, reasons for joint sale, and order generation prompts to constitute the explanatory information. This explanatory information allows the first target audience to understand the functions of the items in the combination and the reasons for selling them together, encouraging them to add the items in the combination to their explanatory item list, improving their decision-making efficiency. Furthermore, this explanatory information can be used as a reference for the first target audience, saving them significant time in organizing their own explanatory statements and improving the conversion rate of the target live stream.

[0081] To ensure that the generated explanation information conforms to the current live streaming scenario, in some embodiments, the explanation information can be obtained through the following steps: An intelligent agent invokes a large model to analyze preset generation rules, the common sales logic information of item combinations, the item characteristics corresponding to the first item and at least one second item, and the live streaming scenario information to obtain the explanation information. The live streaming scenario information is used to instruct the large model to generate explanation information that conforms to the current live streaming scenario. In this embodiment, by inputting the live streaming scenario information into the large model, the generated explanation information can fit the current live streaming scenario, making the explanation information real-time. Specific implementation methods are described above and will not be repeated here.

[0082] Figure 6 This is a block diagram illustrating an apparatus for determining an item list according to an exemplary embodiment. See also Figure 6 The device includes: The page display module 601 is configured to display a first item on an item page, the item page being used to provide multiple items for the target live streaming room; The item adding module 602 is configured to add the first item to the list of explanatory items in the target live broadcast room in response to a list adding operation of the first item by the first object. The combined display module 603 is configured to display an item combination provided by an agent based on the first item, based on the item page. The item combination includes the first item and at least one second item, and the at least one second item conforms to a co-sale logic with the first item. The agent is used to provide the item combination through a large model. The first combination addition module 604 is configured to add the at least one second item to the explanatory item list in response to a list addition operation of the item combination.

[0083] In some embodiments, the combined display module is configured to perform at least one of the following: Based on the item page, the agent displays a first item combination provided by the first item, where the items in the first item combination have complementary functions. Based on the item page, the agent displays a second item combination provided by the first item, wherein the items in the second item combination belong to the same usage scenario and have a combination relationship in the usage scenario; Based on the item page, the agent displays a third item combination provided by the first item, where the items in the third item combination have a linked purchase relationship. Based on the item page, the agent displays a fourth item combination provided by the agent based on the first item, wherein there is a price gradient among the items in the fourth item combination.

[0084] In some embodiments, the combined display module is configured to perform any of the following: Based on the item page, the system displays the item combination obtained by the agent through a large model, which calculates feature similarity based on the item features of the first item and multiple candidate items. Based on the item page, the combination of items is displayed, which is identified by the agent through the large model based on the historical orders related to the first item. Based on the item page, the system displays the item combination obtained by the agent through the large model based on the item features of the first item and multiple candidate items, using a joint sales logic analysis.

[0085] In some embodiments, the apparatus further includes: The explanation display module is configured to display explanation information for the item combination generated by the intelligent agent through a large model based on the item page. The explanation information includes a summary of the item functions of the item combination and the reasons for selling them together.

[0086] In some embodiments, the item combination includes a combined image, which is generated by the agent based on the item images corresponding to the first item and the at least one second item, respectively.

[0087] In some embodiments, the combined display module is configured to display viewing prompt controls corresponding to at least one second item in the item combination in a preset adjacent area; and to display the item details page of the second item in response to a triggering operation of the viewing prompt control for any second item.

[0088] In some embodiments, the explanatory information is obtained through the following steps: The intelligent agent calls the large model to analyze the preset generation rules, the joint sales logic information of the item combination, and the item characteristics corresponding to the first item and the at least one second item, respectively, to obtain the explanation information. The preset generation rules are used to instruct the large model to gradually generate the opening remarks, item function summary, joint sales reasons, and order generation prompts that constitute the explanation information.

[0089] In some embodiments, the explanatory information is obtained through the following steps: The intelligent agent calls the large model to analyze the preset generation rules, the joint sales logic information of the item combination, the item characteristics corresponding to the first item and the at least one second item, and the live broadcast scene information to obtain the explanation information. The preset generation rules are used to instruct the large model to gradually generate the opening remarks, item function summary, joint sales reasons and order generation prompts to constitute the explanation information. The live broadcast scene information is used to instruct the large model to generate explanation information that conforms to the current live broadcast scene.

[0090] It should be noted that the above-described device for determining the explanatory item list is only illustrated by the division of the functional units described above. In practical applications, the functions can be assigned to different functional units as needed, that is, the internal structure of the computer device can be divided into different functional units to complete all or part of the functions described above. Furthermore, the above-described device for determining the explanatory item list is similar to... Figure 2 The illustrated method for determining the list of items is based on the same concept, and its specific implementation process can be found in the method implementation, which will not be repeated here.

[0091] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0092] Figure 7 This is a block diagram illustrating yet another apparatus for determining an explanatory list of items, according to an exemplary embodiment. See also Figure 7 The device includes: The combination determination module 701 is configured to, in response to the first object's list addition operation for the first item, add the first item to the list of explanatory items in the target live broadcast room, and call the intelligent agent to determine at least one second item that conforms to the co-sale logic with the first item through the large model. The combination providing module 702 is configured to provide the first object with a combination of items consisting of the first item and the at least one second item; The second combination addition module 703 is configured to add the at least one second item to the explanatory item list in response to a list addition operation of the item combination.

[0093] In some embodiments, the combination determination module is configured to perform any of the following: The intelligent agent is invoked to calculate the feature similarity between the first item and multiple candidate items based on the item features of the first item and multiple candidate items through the large model, and to determine at least one second item whose feature similarity reaches a preset threshold from the multiple candidate items. The intelligent agent is invoked to identify, based on the historical orders related to the first item, at least one second item that has a purchase relationship with the first item through the large model; The intelligent agent is invoked to perform a co-sale logic analysis based on the characteristics of the first item and multiple candidate items through the large model, and to determine at least one second item from the multiple candidate items that conforms to the co-sale logic with the first item.

[0094] In some embodiments, the item features corresponding to the first item and the plurality of candidate items respectively include basic attribute features, functional features, applicable population features, and scenario features extracted by the intelligent agent from the item details information corresponding to the first item and the plurality of candidate items respectively.

[0095] It should be noted that the above-described device for determining the explanatory item list is only illustrated by the division of the functional units described above. In practical applications, the functions can be assigned to different functional units as needed, that is, the internal structure of the computer device can be divided into different functional units to complete all or part of the functions described above. Furthermore, the above-described device for determining the explanatory item list is similar to... Figure 5 The illustrated method for determining the list of items is based on the same concept, and its specific implementation process can be found in the method implementation, which will not be repeated here.

[0096] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0097] Computer equipment can be implemented as a terminal. Figure 8 This is a block diagram illustrating a terminal 800 according to an exemplary embodiment. Figure 8 A structural block diagram of a terminal 800 provided in an exemplary embodiment of this disclosure is shown. The terminal 800 may be a smartphone, tablet computer, MP3 player (Moving Picture Experts Group Audio Layer III), MP4 player (Moving Picture Experts Group Audio Layer IV), laptop computer, or desktop computer. The terminal 800 may also be referred to as a user device, portable terminal, laptop terminal, desktop terminal, or other names.

[0098] Typically, terminal 800 includes a processor 801 and a memory 802.

[0099] Processor 801 may include one or more processing cores, such as a quad-core processor or an octa-core processor. Processor 801 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 801 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 801 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 801 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0100] The memory 802 may include one or more computer-readable storage media, which may be non-transitory. The memory 802 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 802 are used to store at least one computer program, which is executed by the processor 801 to implement the method for determining the list of explanatory items provided in the method embodiments of this application.

[0101] In some embodiments, the terminal 800 may also optionally include a peripheral device interface 803 and at least one peripheral device. The processor 801, memory 802, and peripheral device interface 803 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 803 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: a radio frequency circuit 804, a display screen 805, a camera assembly 806, an audio circuit 807, and a power supply 808.

[0102] Peripheral device interface 803 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 801 and memory 802. In some embodiments, processor 801, memory 802 and peripheral device interface 803 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 801, memory 802 and peripheral device interface 803 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0103] The radio frequency (RF) circuit 804 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 804 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 804 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. In some embodiments, the RF circuit 804 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit 804 can communicate with other terminals through at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: the World Wide Web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 804 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0104] Display screen 805 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 805 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 801 for processing. In this case, display screen 805 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 805, disposed on the front panel of terminal 800; in other embodiments, there may be at least two display screens, disposed on different surfaces of terminal 800 or in a folded design; in other embodiments, display screen 805 may be a flexible display screen, disposed on a curved or folded surface of terminal 800. Furthermore, display screen 805 may be configured as a non-rectangular irregular shape, i.e., a non-rectangular screen. Display screen 805 may be made of materials such as LCD (Liquid Crystal Display) or OLED (Organic Light-Emitting Diode).

[0105] The camera assembly 806 is used to acquire images or videos. In some embodiments, the camera assembly 806 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the terminal, and the rear-facing camera is located on the back of the terminal. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions. In some embodiments, the camera assembly 806 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash is a combination of a warm-light flash and a cool-light flash, which can be used for light compensation at different color temperatures.

[0106] The audio circuit 807 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting the sound waves into electrical signals that are input to the processor 801 for processing, or input to the radio frequency circuit 804 to achieve voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each located at a different part of the terminal 800. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert the electrical signals from the processor 801 or the radio frequency circuit 804 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 807 may also include a headphone jack.

[0107] Power supply 808 is used to supply power to the various components in terminal 800. Power supply 808 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 808 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged via a wired line, while a wireless rechargeable battery is a battery that is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0108] Those skilled in the art will understand that Figure 8 The structure shown does not constitute a limitation on terminal 800 and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0109] Figure 9 This is a schematic diagram of a server structure provided in an embodiment of this application. The server 900 can vary significantly due to different configurations or performance. It may include one or more Central Processing Units (CPUs) 901 and one or more memories 902. The one or more memories 902 store at least one computer program, which is loaded and executed by the one or more processors 901 to implement the methods provided in the various method embodiments described above. Of course, the server 900 may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The server 900 may also include other components for implementing device functions, which will not be elaborated upon here.

[0110] In an exemplary embodiment, a computer-readable storage medium is also provided, such as a memory including a computer program that can be executed by a processor to perform the methods in the above embodiments. For example, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0111] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory including instructions, which can be executed by a processor of a computer device, such as a terminal, to complete the method for determining the explanatory list of items described above. Optionally, the computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0112] This disclosure also provides a computer program product, including a computer program / instruction that, when executed by a processor, implements the method for determining the list of explanatory items described above.

[0113] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0114] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for determining an item list, characterized in that, The method includes: The first item is displayed on the item page, which is used to provide items to the target live stream room; In response to the first object's list addition operation for the first item, the first item is added to the list of explanatory items in the target live stream room; Based on the item page, the agent displays an item combination provided by the first item, the item combination including the first item and at least one second item, the at least one second item conforming to a co-selling logic with the first item, and the agent is used to provide the item combination through a large model; In response to the operation of adding items to the list of the item combination, the at least one second item is added to the list of explanatory items.

2. The method for determining the list of explanatory items according to claim 1, characterized in that, The item-based page, which displays a combination of items provided by the agent based on the first item, includes at least one of the following: Based on the item page, the agent displays a first item combination provided by the first item, where the items in the first item combination have complementary functions. Based on the item page, the agent displays a second item combination provided by the first item, wherein the items in the second item combination belong to the same usage scenario and have a combination relationship in the usage scenario; Based on the item page, the agent displays a third item combination provided by the first item, where the items in the third item combination have a linked purchase relationship. Based on the item page, the agent displays a fourth item combination provided by the first item, where there are price gradients among the items in the fourth item combination. Based on the item page, the agent displays a fifth item combination provided by the first item, wherein the items in the fifth item combination belong to the same style.

3. The method for determining the list of explanatory items according to claim 1, characterized in that, The item-based page, which displays the combination of items provided by the agent based on the first item, includes any of the following: Based on the item page, the system displays the item combination obtained by the agent through a large model, which calculates feature similarity based on the item features of the first item and multiple candidate items. Based on the item page, the combination of items is displayed, which is identified by the agent through the large model based on the historical orders related to the first item. Based on the item page, the system displays the item combination obtained by the agent through the large model based on the item features of the first item and multiple candidate items, using a joint sales logic analysis.

4. The method for determining the list of explanatory items according to claim 1, characterized in that, The method further includes: Based on the item page, the intelligent agent displays explanatory information for the item combination generated by the large model. The explanatory information includes a summary of the item functions of the item combination and the reasons for selling them together.

5. The method for determining the list of explanatory items according to claim 1, characterized in that, The item combination includes a combined image, which is generated by the agent based on the item images corresponding to the first item and the at least one second item, respectively.

6. The method for determining the list of explanatory items according to claim 1, characterized in that, The method further includes: In the item combination, in the preset adjacent area corresponding to at least one second item, a viewing prompt control corresponding to each of the at least one second item is displayed; In response to the triggering of the view prompt control for any second item, the item details page for the second item is displayed.

7. The method for determining the list of explanatory items according to claim 4, characterized in that, The explanatory information is obtained through the following steps: The intelligent agent calls the large model to analyze the preset generation rules, the joint sales logic information of the item combination, and the item characteristics corresponding to the first item and the at least one second item, respectively, to obtain the explanation information. The preset generation rules are used to instruct the large model to gradually generate the opening remarks, item function summary, joint sales reasons, and order generation prompts that constitute the explanation information.

8. The method for determining the list of explanatory items according to claim 4, characterized in that, The explanatory information is obtained through the following steps: The intelligent agent calls the large model to analyze the preset generation rules, the joint sales logic information of the item combination, the item characteristics corresponding to the first item and the at least one second item, and the live broadcast scene information to obtain the explanation information. The preset generation rules are used to instruct the large model to gradually generate the opening remarks, item function summary, joint sales reasons and order generation prompts to constitute the explanation information. The live broadcast scene information is used to instruct the large model to generate explanation information that conforms to the current live broadcast scene.

9. A method for determining an item list, characterized in that, The method includes: In response to the first object's operation of adding the first item to the list, the first item is added to the list of items to be explained in the target live broadcast room, and the intelligent agent is invoked to determine at least one second item that conforms to the co-sale logic with the first item through the large model. Provide the first object with a combination of items consisting of the first item and the at least one second item; In response to the operation of adding items to the list of the item combination, the at least one second item is added to the list of explanatory items.

10. The method for determining the list of explanatory items according to claim 9, characterized in that, The calling agent determines, through a large model, at least one second item that conforms to the co-sale logic with the first item, including any of the following: The intelligent agent is invoked to calculate the feature similarity between the first item and multiple candidate items based on the item features of the first item and multiple candidate items through the large model, and to determine at least one second item whose feature similarity reaches a preset threshold from the multiple candidate items. The intelligent agent is invoked to identify, based on the historical orders related to the first item, at least one second item that has a purchase relationship with the first item through the large model; The intelligent agent is invoked to perform a co-sale logic analysis based on the characteristics of the first item and multiple candidate items through the large model, and to determine at least one second item from the multiple candidate items that conforms to the co-sale logic with the first item.

11. The method for determining the list of explanatory items according to claim 10, characterized in that, The item features corresponding to the first item and the multiple candidate items respectively include basic attribute features, functional features, applicable user features, and scenario features extracted by the intelligent agent from the item details information corresponding to the first item and the multiple candidate items respectively.

12. A device for determining an item list, characterized in that, include: The page display module is configured to display a first item on an item page, which is used to provide multiple items for the target live stream room; The item addition module is configured to add the first item to the list of explanatory items in the target live broadcast room in response to a list addition operation of the first object for the first item. The combined display module is configured to display an item combination provided by an agent based on the first item, on the item page. The item combination includes the first item and at least one second item, and the at least one second item conforms to a co-sale logic with the first item. The agent is used to provide the item combination through a large model. The first combination addition module is configured to add the at least one second item to the explanatory item list in response to a list addition operation of the item combination.

13. A device for determining an item list, characterized in that, include: The combination determination module is configured to, in response to the first object's list addition operation for the first item, add the first item to the list of explanatory items in the target live broadcast room, and call the intelligent agent to determine at least one second item that conforms to the co-sale logic with the first item through the large model. A combination providing module is configured to provide the first object with a combination of items consisting of the first item and the at least one second item; The second combination addition module is configured to add the at least one second item to the explanatory item list in response to a list addition operation of the item combination.

14. A computer device, characterized in that, The computer device includes: One or more processors; Memory used to store the executable program code of the processor; The processor is configured to execute the program code to implement the method for determining the list of explanatory items as described in any one of claims 1 to 11.

15. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of a computer device, the computer device is enabled to perform the method for determining the list of explanatory items as described in any one of claims 1 to 11.

16. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method for determining the list of explanatory items as described in any one of claims 1 to 11.

Images